Skills
skills/jeremylongshore/claude-code-plugins-plus-skills/mistral-sdk-patterns/Gen Agent Trust Hub

mistral-sdk-patterns

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines functions for handling chat completions that ingest untrusted message data, creating a potential surface for indirect prompt injection.
  • Ingestion points: The messages parameter in the chat and streamChat functions within SKILL.md.
  • Boundary markers: The provided code patterns do not include explicit delimiters or instructions to ignore embedded commands within the message content.
  • Capability inventory: The skill is configured with Read, Write, and Edit tool permissions, which could be targeted by successful injection attacks.
  • Sanitization: No sanitization, validation, or filtering of the message content is implemented in the code templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 11:28 AM